Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866914129196875776 |
|---|---|
| author | Xie, Ren-Dong He, Zhi-Fen Li, Bo Liu, Bin Hu, Jin-Yan |
| author_facet | Xie, Ren-Dong He, Zhi-Fen Li, Bo Liu, Bin Hu, Jin-Yan |
| contents | Multi-label image classification is a critical task in machine learning that aims to accurately assign multiple labels to a single image. While existing methods often utilize attention mechanisms or graph convolutional networks to model visual representations, their performance is still constrained by two critical limitations: the inability to learn discriminative semantic-aware features, and the lack of fine-grained alignment between visual representations and label embeddings. To tackle these issues in a unified framework, this paper proposes a novel approach named Semantic-aware representation learning via Conditional Transport for Multi-Label Image Classification (SCT). The proposed method introduces a semantic-related feature learning module that extracts discriminative label-specific features by emphasizing semantic relevance and interaction, along with a conditional transport-based alignment mechanism that enables precise visual-semantic alignment. Extensive experiments on two widely-used benchmark datasets, VOC2007 and MS-COCO, validate the effectiveness of SCT and demonstrate its superior performance compared to existing state-of-the-art methods. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_14918 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification Xie, Ren-Dong He, Zhi-Fen Li, Bo Liu, Bin Hu, Jin-Yan Computer Vision and Pattern Recognition Multi-label image classification is a critical task in machine learning that aims to accurately assign multiple labels to a single image. While existing methods often utilize attention mechanisms or graph convolutional networks to model visual representations, their performance is still constrained by two critical limitations: the inability to learn discriminative semantic-aware features, and the lack of fine-grained alignment between visual representations and label embeddings. To tackle these issues in a unified framework, this paper proposes a novel approach named Semantic-aware representation learning via Conditional Transport for Multi-Label Image Classification (SCT). The proposed method introduces a semantic-related feature learning module that extracts discriminative label-specific features by emphasizing semantic relevance and interaction, along with a conditional transport-based alignment mechanism that enables precise visual-semantic alignment. Extensive experiments on two widely-used benchmark datasets, VOC2007 and MS-COCO, validate the effectiveness of SCT and demonstrate its superior performance compared to existing state-of-the-art methods. |
| title | Semantic-Aware Representation Learning via Conditional Transport for Multi-Label Image Classification |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.14918 |